diff --git a/llama.cpp b/llama.cpp index 4971fa0ab..cfca3a6a3 100644 --- a/llama.cpp +++ b/llama.cpp @@ -6517,8 +6517,6 @@ struct llm_build_context { ext_factor, attn_factor, beta_fast, beta_slow ); cb(Kcur, "Kcur", il); - - cur = llm_build_kv(ctx0, model, hparams, kv_self, gf, model.layers[il].wo, NULL, Kcur, Vcur, Qcur, KQ_mask, KQ_pos, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il);